discord
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard wrapper for the Discord API and does not contain any malicious patterns or obfuscated code.
- [DATA_EXPOSURE]: The skill handles untrusted data by design (reading Discord messages), which presents a standard surface for indirect prompt injection.
- Ingestion points: The script reads message content, attachments, and metadata from Discord via
message list,message get, andmessage searchcommands inscripts/discord_cli.py. - Boundary markers: The CLI tool outputs data in structured JSON format, providing clear boundaries for the agent.
- Capability inventory: The script allows the agent to send, edit, and delete messages, manage reactions, create threads, and modify pins within Discord.
- Sanitization: The script performs standard JSON parsing and encoding for all API interactions. It provides the agent with raw message content from Discord, which may contain instructions from external users.
Audit Metadata